arXiv subjects

Damien van de Berg

Publications and source records attributed to Damien van de Berg.

3 recordsLinked to original sources

arXiv2024

Surrogate-Based Optimization Techniques for Process Systems Engineering

Optimization plays an important role in chemical engineering, impacting cost-effectiveness, resource utilization, product quality, and process sustainability metrics. This chapter broadly focuses on data-driven optimization, particularly, on model-based derivative-free techniques, also known as surrogate-based optimization. The chapter introduces readers to the theory and practical considerations of various algorithms, complemented by a performance assessment across multiple dimensions, test functions, and two chemical engineering case studies: a stochastic high-dimensional reactor control study and a low-dimensional constrained stochastic reactor optimization study. This assessment sheds light on each algorithm's performance and suitability for diverse applications. Additionally, each algorithm is accompanied by background information, mathematical foundations, and algorithm descriptions. Among the discussed algorithms are Bayesian Optimization (BO), including state-of-the-art TuRBO, Constrained Optimization by Linear Approximation (COBYLA), the Ensemble Tree Model Optimization Tool (ENTMOOT) which uses decision trees as surrogates, Stable Noisy Optimization by Branch and Fit (SNOBFIT), methods that use radial basis functions such as DYCORS and SRBFStrategy, Constrained Optimization by Quadratic Approximations (COBYQA), as well as a few others recognized for their effectiveness in surrogate-based optimization. By combining theory with practice, this chapter equips readers with the knowledge to integrate surrogate-based optimization techniques into chemical engineering. The overarching aim is to highlight the advantages of surrogate-based optimization, introduce state-of-the-art algorithms, and provide guidance for successful implementation within process systems engineering.

math.OC↗

arXiv2023

Hierarchical planning-scheduling-control -- Optimality surrogates and derivative-free optimization

Planning, scheduling, and control typically constitute separate decision-making units within chemical companies. Traditionally, their integration is modelled sequentially, but recent efforts prioritize lower-level feasibility and optimality, leading to large-scale, potentially multi-level, hierarchical formulations. Data-driven techniques, like optimality surrogates or derivative-free optimization, become essential in addressing ensuing tractability challenges. We demonstrate a step-by-step workflow to find a tractable solution to a tri-level formulation of a multi-site, multi-product planning-scheduling-control case study. We discuss solution tractability-accuracy trade-offs and scaling properties for both methods. Despite individual improvements over conventional heuristics, both approaches present drawbacks. Consequently, we synthesize our findings into a methodology combining their strengths. Our approach remains agnostic to the level-specific formulations when the linking variables are identified and retains the heuristic sequential solution as fallback option. We advance the field by leveraging parallelization, hyperparameter tuning, and a combination of off- and on-line computation, to find tractable solutions to more accurate multi-level formulations.

math.OC↗

arXiv2023

An Analysis of Multi-Agent Reinforcement Learning for Decentralized Inventory Control Systems

Most solutions to the inventory management problem assume a centralization of information that is incompatible with organisational constraints in real supply chain networks. The inventory management problem is a well-known planning problem in operations research, concerned with finding the optimal re-order policy for nodes in a supply chain. While many centralized solutions to the problem exist, they are not applicable to real-world supply chains made up of independent entities. The problem can however be naturally decomposed into sub-problems, each associated with an independent entity, turning it into a multi-agent system. Therefore, a decentralized data-driven solution to inventory management problems using multi-agent reinforcement learning is proposed where each entity is controlled by an agent. Three multi-agent variations of the proximal policy optimization algorithm are investigated through simulations of different supply chain networks and levels of uncertainty. The centralized training decentralized execution framework is deployed, which relies on offline centralization during simulation-based policy identification, but enables decentralization when the policies are deployed online to the real system. Results show that using multi-agent proximal policy optimization with a centralized critic leads to performance very close to that of a centralized data-driven solution and outperforms a distributed model-based solution in most cases while respecting the information constraints of the system.

cs.LG↗